{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:NKAVD4T6MI6S55ZQRBQBTKGQP5","short_pith_number":"pith:NKAVD4T6","canonical_record":{"source":{"id":"2111.09883","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-18T18:59:33Z","cross_cats_sorted":[],"title_canon_sha256":"48b9535f65caedf6e4285182234ab91110e79e27f8e894406cea8e5110413f85","abstract_canon_sha256":"e8dcaa827f0746bc37d617013ae426bf74f94e2f0d6d5e19a397923e6c05f517"},"schema_version":"1.0"},"canonical_sha256":"6a8151f27e623d2ef730886019a8d07f6b436545b2f5eabacccd87d3e366e231","source":{"kind":"arxiv","id":"2111.09883","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.09883","created_at":"2026-07-05T04:13:11Z"},{"alias_kind":"arxiv_version","alias_value":"2111.09883v2","created_at":"2026-07-05T04:13:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.09883","created_at":"2026-07-05T04:13:11Z"},{"alias_kind":"pith_short_12","alias_value":"NKAVD4T6MI6S","created_at":"2026-07-05T04:13:11Z"},{"alias_kind":"pith_short_16","alias_value":"NKAVD4T6MI6S55ZQ","created_at":"2026-07-05T04:13:11Z"},{"alias_kind":"pith_short_8","alias_value":"NKAVD4T6","created_at":"2026-07-05T04:13:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:NKAVD4T6MI6S55ZQRBQBTKGQP5","target":"record","payload":{"canonical_record":{"source":{"id":"2111.09883","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-18T18:59:33Z","cross_cats_sorted":[],"title_canon_sha256":"48b9535f65caedf6e4285182234ab91110e79e27f8e894406cea8e5110413f85","abstract_canon_sha256":"e8dcaa827f0746bc37d617013ae426bf74f94e2f0d6d5e19a397923e6c05f517"},"schema_version":"1.0"},"canonical_sha256":"6a8151f27e623d2ef730886019a8d07f6b436545b2f5eabacccd87d3e366e231","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:11.426218Z","signature_b64":"Uo5/bGNL3FHGm05s9j7HZCLs2xgR9etSJtDQLaj2Va5BAihReezOvGIC7bTEoxnDTLG7623iyjtYUDmrZlouCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a8151f27e623d2ef730886019a8d07f6b436545b2f5eabacccd87d3e366e231","last_reissued_at":"2026-07-05T04:13:11.425730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:11.425730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.09883","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:13:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NO1XWZ94lL27gkxgCL/SVu3IO/4AmroKvMCboMRUcHtS5oH6X6RTonfelRj5D9QcIfJtIgVC/m61xmMDylqpAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:51:39.597507Z"},"content_sha256":"0d081cad3d022afd7e1d8aa8573c9984a1111d14b15924d9e41db4dd310cb66e","schema_version":"1.0","event_id":"sha256:0d081cad3d022afd7e1d8aa8573c9984a1111d14b15924d9e41db4dd310cb66e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:NKAVD4T6MI6S55ZQRBQBTKGQP5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Swin Transformer V2: Scaling Up Capacity and Resolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Furu Wei, Han Hu, Jia Ning, Li Dong, Yixuan Wei, Yue Cao, Yutong Lin, Ze Liu, Zhenda Xie, Zheng Zhang, Zhuliang Yao","submitted_at":"2021-11-18T18:59:33Z","abstract_excerpt":"Large-scale NLP models have been shown to significantly improve the performance on language tasks with no signs of saturation. They also demonstrate amazing few-shot capabilities like that of human beings. This paper aims to explore large-scale models in computer vision. We tackle three major issues in training and application of large vision models, including training instability, resolution gaps between pre-training and fine-tuning, and hunger on labelled data. Three main techniques are proposed: 1) a residual-post-norm method combined with cosine attention to improve training stability; 2) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.09883","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.09883/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:13:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AEBPTKy0KEMyX0cLjH+ZhUX5utLq9/o62MiSQmeTz73B+yY9bXsw0fQ7UC8AtMcsIjZBJQoa2HWBlxyg208LDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:51:39.598075Z"},"content_sha256":"fc99d23d900f996504de19bc1cf1681c6822086935db95593449c327dd2346c1","schema_version":"1.0","event_id":"sha256:fc99d23d900f996504de19bc1cf1681c6822086935db95593449c327dd2346c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NKAVD4T6MI6S55ZQRBQBTKGQP5/bundle.json","state_url":"https://pith.science/pith/NKAVD4T6MI6S55ZQRBQBTKGQP5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NKAVD4T6MI6S55ZQRBQBTKGQP5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T18:51:39Z","links":{"resolver":"https://pith.science/pith/NKAVD4T6MI6S55ZQRBQBTKGQP5","bundle":"https://pith.science/pith/NKAVD4T6MI6S55ZQRBQBTKGQP5/bundle.json","state":"https://pith.science/pith/NKAVD4T6MI6S55ZQRBQBTKGQP5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NKAVD4T6MI6S55ZQRBQBTKGQP5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NKAVD4T6MI6S55ZQRBQBTKGQP5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e8dcaa827f0746bc37d617013ae426bf74f94e2f0d6d5e19a397923e6c05f517","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-18T18:59:33Z","title_canon_sha256":"48b9535f65caedf6e4285182234ab91110e79e27f8e894406cea8e5110413f85"},"schema_version":"1.0","source":{"id":"2111.09883","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.09883","created_at":"2026-07-05T04:13:11Z"},{"alias_kind":"arxiv_version","alias_value":"2111.09883v2","created_at":"2026-07-05T04:13:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.09883","created_at":"2026-07-05T04:13:11Z"},{"alias_kind":"pith_short_12","alias_value":"NKAVD4T6MI6S","created_at":"2026-07-05T04:13:11Z"},{"alias_kind":"pith_short_16","alias_value":"NKAVD4T6MI6S55ZQ","created_at":"2026-07-05T04:13:11Z"},{"alias_kind":"pith_short_8","alias_value":"NKAVD4T6","created_at":"2026-07-05T04:13:11Z"}],"graph_snapshots":[{"event_id":"sha256:fc99d23d900f996504de19bc1cf1681c6822086935db95593449c327dd2346c1","target":"graph","created_at":"2026-07-05T04:13:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2111.09883/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale NLP models have been shown to significantly improve the performance on language tasks with no signs of saturation. They also demonstrate amazing few-shot capabilities like that of human beings. This paper aims to explore large-scale models in computer vision. We tackle three major issues in training and application of large vision models, including training instability, resolution gaps between pre-training and fine-tuning, and hunger on labelled data. Three main techniques are proposed: 1) a residual-post-norm method combined with cosine attention to improve training stability; 2) ","authors_text":"Baining Guo, Furu Wei, Han Hu, Jia Ning, Li Dong, Yixuan Wei, Yue Cao, Yutong Lin, Ze Liu, Zhenda Xie, Zheng Zhang, Zhuliang Yao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-18T18:59:33Z","title":"Swin Transformer V2: Scaling Up Capacity and Resolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.09883","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0d081cad3d022afd7e1d8aa8573c9984a1111d14b15924d9e41db4dd310cb66e","target":"record","created_at":"2026-07-05T04:13:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e8dcaa827f0746bc37d617013ae426bf74f94e2f0d6d5e19a397923e6c05f517","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-18T18:59:33Z","title_canon_sha256":"48b9535f65caedf6e4285182234ab91110e79e27f8e894406cea8e5110413f85"},"schema_version":"1.0","source":{"id":"2111.09883","kind":"arxiv","version":2}},"canonical_sha256":"6a8151f27e623d2ef730886019a8d07f6b436545b2f5eabacccd87d3e366e231","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a8151f27e623d2ef730886019a8d07f6b436545b2f5eabacccd87d3e366e231","first_computed_at":"2026-07-05T04:13:11.425730Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:13:11.425730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uo5/bGNL3FHGm05s9j7HZCLs2xgR9etSJtDQLaj2Va5BAihReezOvGIC7bTEoxnDTLG7623iyjtYUDmrZlouCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:13:11.426218Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.09883","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d081cad3d022afd7e1d8aa8573c9984a1111d14b15924d9e41db4dd310cb66e","sha256:fc99d23d900f996504de19bc1cf1681c6822086935db95593449c327dd2346c1"],"state_sha256":"e781c991b727c1bf4bbe012b82d0e8c591a9e214d862d9f1b30361a71ed802e6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kIb+asx5rGfTH6wPkRTbe6B8hG1GTys7AvbpTKCUHVGMShzwRFt6bPygJGlJY9nA5ql+xCHKWo9CEx+O7ISiBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:51:39.604948Z","bundle_sha256":"75acc2e67390a85797215ef04a4432647a1d9c07a6e827b0b74b1de9b2c47954"}}